专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08170874B2 Apparatus and method for recognizing speech based on feature parameters of modified speech and playing back the modified speech 有权
标题翻译：基于修改语音的特征参数来识别语音并回放修改语音的装置和方法
公开(公告)号：US08170874B2
公开(公告)日：2012-05-01
申请号：US12165793
申请日：2008-07-01
申请人： Masayuki Yamada , Toshiaki Fukada , Yasuo Okutani , Michio Aizawa
发明人： Masayuki Yamada , Toshiaki Fukada , Yasuo Okutani , Michio Aizawa
IPC分类号： G10L15/00 , G10L21/00
CPC分类号： G10L15/065 , G10L21/0208 , G10L2015/0631
摘要： A speech recognition apparatus which improves the sound quality of speech output as a speech recognition result is provided. The speech recognition apparatus includes a recognition unit, which recognizes speech based on a recognition dictionary, and a registration unit, which registers a dictionary entry of a new recognition word in the recognition dictionary. The recognition unit includes a generation unit, which generates a dictionary entry including speech of the new recognition word item and feature parameters of the speech, and a modification unit, which makes a modification for improving the sound quality of the speech included in the dictionary entry generated by the generation unit. The recognition unit includes a speech output unit, which outputs speech which is included in a dictionary entry corresponding to the recognition result of input speech, and is modified by the modification unit.
摘要翻译：提供了一种提高作为语音识别结果的语音输出的声音质量的语音识别装置。语音识别装置包括：识别单元，其基于识别字典识别语音;以及登记单元，其在识别词典中登记新识别词的字典条目。识别单元包括：生成单元，生成包括新的识别词项的语音和语音的特征参数的字典项;以及修改单元，其对修改包括在字典项中的语音的声音质量进行修改由生成单元生成。识别单元包括语音输出单元，其输出包括在与输入语音的识别结果相对应的字典条目中的语音，并由修改单元修改。

2. 发明申请

US20090012790A1 SPEECH RECOGNITION APPARATUS AND CONTROL METHOD THEREOF 有权
标题翻译：语音识别装置及其控制方法
公开(公告)号：US20090012790A1
公开(公告)日：2009-01-08
申请号：US12165793
申请日：2008-07-01
申请人： Masayuki Yamada , Toshiaki Fukada , Yasuo Okutani , Michio Aizawa
发明人： Masayuki Yamada , Toshiaki Fukada , Yasuo Okutani , Michio Aizawa
IPC分类号： G10L15/00
CPC分类号： G10L15/065 , G10L21/0208 , G10L2015/0631
摘要： A speech recognition apparatus which improves the sound quality of speech output as a speech recognition result is provided. The speech recognition apparatus includes a recognition unit, which recognizes speech based on a recognition dictionary, and a registration unit, which registers a dictionary entry of a new recognition word in the recognition dictionary. The recognition unit includes a generation unit, which generates a dictionary entry including speech of the new recognition word item and feature parameters of the speech, and a modification unit, which makes a modification for improving the sound quality of the speech included in the dictionary entry generated by the generation unit. The recognition unit includes a speech output unit, which outputs speech which is included in a dictionary entry corresponding to the recognition result of input speech, and is modified by the modification unit.
摘要翻译：提供了一种提高作为语音识别结果的语音输出的声音质量的语音识别装置。语音识别装置包括：识别单元，其基于识别字典识别语音;以及登记单元，其在识别词典中登记新识别词的字典条目。识别单元包括：生成单元，生成包括新的识别词项的语音和语音的特征参数的字典项;以及修改单元，其对修改包括在字典项中的语音的声音质量进行修改由生成单元生成。识别单元包括语音输出单元，其输出包括在与输入语音的识别结果相对应的字典条目中的语音，并由修改单元修改。

3. 发明授权

US08041569B2 Speech synthesis method and apparatus using pre-recorded speech and rule-based synthesized speech 有权
标题翻译：使用预录制语音和基于规则的合成语音的语音合成方法和装置
公开(公告)号：US08041569B2
公开(公告)日：2011-10-18
申请号：US12035789
申请日：2008-02-22
申请人： Yasuo Okutani , Michio Aizawa , Toshiaki Fukada
发明人： Yasuo Okutani , Michio Aizawa , Toshiaki Fukada
IPC分类号： G10L13/00 , G10L13/08
CPC分类号： G10L13/06
摘要： A language processing unit identifies a word by performing language analysis on a text supplied from a text holding unit. A synthesis selection unit selects speech synthesis processing performed by a rule-based synthesis unit or speech synthesis processing performed by a pre-recorded-speech-based synthesis unit for a word of interest extracted from the language analysis result. The selected rule-based synthesis unit or pre-recorded-speech-based synthesis unit executes speech synthesis processing for the word of interest.
摘要翻译：语言处理单元通过对从文本保持单元提供的文本执行语言分析来识别单词。综合选择单元选择通过基于规则的合成单元执行的语音合成处理或者由从语言分析结果提取的用于感兴趣的词的基于预先记录的基于语音的合成单元执行的语音合成处理。所选择的基于规则的合成单元或预先录制的基于语音的合成单元对所关心的词进行语音合成处理。

4. 发明申请

US20080228487A1 SPEECH SYNTHESIS APPARATUS AND METHOD 有权
标题翻译：语音合成设备和方法
公开(公告)号：US20080228487A1
公开(公告)日：2008-09-18
申请号：US12035789
申请日：2008-02-22
申请人： Yasuo Okutani , Michio Aizawa , Toshiaki Fukada
发明人： Yasuo Okutani , Michio Aizawa , Toshiaki Fukada
IPC分类号： G10L13/06
CPC分类号： G10L13/06
摘要： A language processing unit identifies a word by performing language analysis on a text supplied from a text holding unit. A synthesis selection unit selects speech synthesis processing performed by a rule-based synthesis unit or speech synthesis processing performed by a pre-recorded-speech-based synthesis unit for a word of interest extracted from the language analysis result. The selected rule-based synthesis unit or pre-recorded-speech-based synthesis unit executes speech synthesis processing for the word of interest.
摘要翻译：语言处理单元通过对从文本保持单元提供的文本执行语言分析来识别单词。综合选择单元选择通过基于规则的合成单元执行的语音合成处理或者由从语言分析结果提取的用于感兴趣的词的基于预先记录的基于语音的合成单元执行的语音合成处理。所选择的基于规则的合成单元或预先录制的基于语音的合成单元对所关心的词进行语音合成处理。

5. 发明申请

US20080177548A1 Speech Synthesis Method and Apparatus 审中-公开
标题翻译：语音合成方法与装置
公开(公告)号：US20080177548A1
公开(公告)日：2008-07-24
申请号：US11579864
申请日：2006-05-29
申请人： Masayuki Yamada , Yasuo Okutani , Michio Aizawa
发明人： Masayuki Yamada , Yasuo Okutani , Michio Aizawa
IPC分类号： G10L13/08
CPC分类号： G10L13/10 , G10L13/07
摘要： A speech synthesis method includes selecting a segment, determining whether to conduct prosodic modification on the selected segment, calculating a target value of prosodic modification of a segment on which prosodic modification has been determined to be conducted based on a result of the determination, conducting prosodic modification such that a prosody of the segment on which prosodic modification has been determined to be conducted takes the target value of prosodic modification, and concatenating the segment on which prosodic modification has been conducted or a segment on which prosodic modification has been determined not to be conducted as a result of the determination.
摘要翻译：一种语音合成方法，包括：选择一段，确定是否对所选段进行韵律修改;根据确定结果，计算出已经确定要进行韵律修饰的段的韵律修饰的目标值，进行韵律修改，使得已经确定了韵律修饰的片段的韵律取韵律修饰的目标值，并且连接已经进行韵律修饰的片段或已经确定韵律修饰的片段不被确定作为决定的结果。

6. 发明申请

US20060031072A1 Electronic dictionary apparatus and its control method 审中-公开
标题翻译：电子词典装置及其控制方法
公开(公告)号：US20060031072A1
公开(公告)日：2006-02-09
申请号：US11197268
申请日：2005-08-04
申请人： Yasuo Okutani , Michio Aizawa
发明人： Yasuo Okutani , Michio Aizawa
IPC分类号： G10L13/08
CPC分类号： G10L13/08
摘要： An electronic dictionary apparatus and its control method are provided. A database contains entry words and advanced phonetic information corresponding to each entry word. A dictionary search section searches the database using an entry word specified by a user as a search key and acquires the advanced phonetic information corresponding to the entry word. A display section displays simple phonetic information generated based on the acquired advanced phonetic information. A speech output section performs speech synthesis based on the acquired advanced phonetic information and outputs the synthesized speech.
摘要翻译：提供电子词典装置及其控制方法。数据库包含与每个条目词对应的入口词和高级语音信息。字典搜索部分使用由用户指定的条目词作为搜索关键字来搜索数据库，并获取对应于入口词的高级语音信息。显示部分显示基于所获取的高级语音信息生成的简单语音信息。语音输出部分基于所获取的高级语音信息执行语音合成，并输出合成语音。

7. 发明申请

US20060200352A1 Speech synthesis method 审中-公开
标题翻译：语音合成方法
公开(公告)号：US20060200352A1
公开(公告)日：2006-09-07
申请号：US11355300
申请日：2006-02-15
申请人： Michio Aizawa , Yasuo Okutani
发明人： Michio Aizawa , Yasuo Okutani
IPC分类号： G10L13/08
CPC分类号： G10L13/07 , G10L13/04
摘要： In a phoneme-selection-type speech synthesis apparatus, sound quality when a suitable phoneme is not found is prevented from being deteriorated without changing an input sentence. A plurality of pieces of reading prosody information are obtained. The cost when an optimum phoneme sequence is selected with respect to each of the plurality of pieces of reading prosody information is calculated. Speech with respect to the reading prosody information in which the cost is minimized is synthesized.
摘要翻译：在音素选择型语音合成装置中，在不改变输入的句子的情况下，防止没有发现合适的音素的声音质量劣化。获得多条阅读韵律信息。计算相对于多条读取韵律信息中的每一条选择最佳音素序列的成本。关于成本最小化的阅读韵律信息的语音合成。

8. 发明申请

US20070118383A1 SPEECH OUTPUT METHOD 有权
标题翻译：语音输出方法
公开(公告)号：US20070118383A1
公开(公告)日：2007-05-24
申请号：US11553097
申请日：2006-10-26
申请人： Toshiaki Fukada , Michio Aizawa
发明人： Toshiaki Fukada , Michio Aizawa
IPC分类号： G10L21/00
CPC分类号： G10L13/00
摘要： In order to prevent or reduce setting errors, a speech output of information concerning the contents of settings is produced so that important setting information can be output as speech to users. The present invention is directed to an apparatus and method for outputting setting information via speech, the apparatus and method including changing a plurality of preset setting values based on user input, detecting changes in the setting values, determining a priority according to which setting information is to be output as speech according to the detected changes, and producing a speech output of the setting information according to the priority.
摘要翻译：为了防止或减少设置错误，产生关于设置内容的信息的语音输出，使得可以将重要的设置信息作为语音输出给用户。本发明涉及一种用于经由语音输出设置信息的装置和方法，所述装置和方法包括：基于用户输入改变多个预设设置值，检测设置值的变化，根据哪个设置信息确定优先级根据检测到的变化作为语音输出，并根据优先级产生设置信息的语音输出。

9. 发明授权

US07809571B2 Speech output of setting information according to determined priority 有权
标题翻译：根据确定的优先级设置信息的语音输出
公开(公告)号：US07809571B2
公开(公告)日：2010-10-05
申请号：US11553097
申请日：2006-10-26
申请人： Toshiaki Fukada , Michio Aizawa
发明人： Toshiaki Fukada , Michio Aizawa
IPC分类号： G10L13/00
CPC分类号： G10L13/00
摘要： In order to prevent or reduce setting errors, a speech output of information concerning the contents of settings is produced so that important setting information can be output as speech to users. The present invention is directed to an apparatus and method for outputting setting information via speech, the apparatus and method including changing a plurality of preset setting values based on user input, detecting changes in the setting values, determining a priority according to which setting information is to be output as speech according to the detected changes, and producing a speech output of the setting information according to the priority.
摘要翻译：为了防止或减少设置错误，产生关于设置内容的信息的语音输出，使得可以将重要的设置信息作为语音输出给用户。本发明涉及一种用于经由语音输出设置信息的装置和方法，所述装置和方法包括：基于用户输入改变多个预设设置值，检测设置值的变化，根据哪个设置信息确定优先级根据检测到的变化作为语音输出，并根据优先级产生设置信息的语音输出。

10. 发明授权

US07376566B2 Image forming apparatus and method 有权
标题翻译：图像形成装置及方法
公开(公告)号：US07376566B2
公开(公告)日：2008-05-20
申请号：US10754533
申请日：2004-01-12
申请人： Michio Aizawa , Tsuyoshi Yagisawa , Masayuki Yamada
发明人： Michio Aizawa , Tsuyoshi Yagisawa , Masayuki Yamada
IPC分类号： G10L21/00
CPC分类号： H04N1/00915 , G10L2015/228 , H04N1/00326 , H04N2201/007 , H04N2201/0082
摘要： Provided are an image forming apparatus and an image forming method in which a decline in the recognition rate of voice recognition ascribable to operating sound during printing can be prevented by starting voice recognition after the printing operation has been suspended. The image forming apparatus is provided with a voice recognition unit (103) for recognizing entered voice, and a image printing unit (107) for printing prescribed print information. Whether the image printing unit (107) is currently printing is discriminated by an image-printing-state holding unit (106). Further, a request to start operation of a voice recognition unit (103) is accepted. If the request to start operation of the voice recognition unit (103) is accepted during printing of print information by the image printing unit (107), then printing of the print information by the image printing unit (107) is suspended. The state of a voice-recognition-state holding unit (102) is then changed and the voice recognition unit (103) starts performing recognition of input voice.
摘要翻译：提供了一种图像形成装置和图像形成方法，其中可以通过在打印操作已经暂停之后开始语音识别来防止在打印期间归因于操作声音的语音识别识别率的下降。图像形成装置具有用于识别输入的声音的语音识别单元（103）和用于打印规定的打印信息的图像打印单元（107）。图像打印单元（107）当前正在打印是由图像打印状态保持单元（106）来识别的。此外，接受语音识别单元（103）的开始操作的请求。如果在由图像打印单元（107）打印打印信息期间接受语音识别单元（103）的开始操作的请求，则暂停由图像打印单元（107）打印打印信息。然后，语音识别状态保持单元（102）的状态被改变，并且语音识别单元（103）开始执行输入语音的识别。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式